SIPLAB: Sensing, Interaction & Perception Lab

The SIPLAB at ETH Zürich is an interdisciplinary research lab working on egocentric perception, computational interaction, and digital biomarkers. We advance mixed reality, robotics, human-computer inter­action, and precision medicine. We are part of the Department of Computer Science and the AI Center.

egocentric perception scalable methods for action & motion tracking
computational interaction decoding input intent for adaptive systems
digital biomarkers signal processing for mobile health

Projects to appear and recent research

NeurIPS 2025 (December)

Contimask

Explaining Irregular Time Series via Perturbations in Continuous Time
NeurIPS 2025 (December)

Learning Without Augmenting

Unsupervised Time Series Representation Learning via Frame Projections
NeurIPS 2025 (December)

egoEMOTION

Emotion and Personality Recognition using Egocentric Systems
ICCV 2025 (October)

Group Inertial Poser

Multi-Person Pose and Global Translation from Sparse Inertial Sensors and Ultra-Wideband Ranging
ACM IVA 2025 (September)

Personality-Emotion Framework

A joint framework for conversational agents

Affiliations and collaborations